INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or names

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

town

-0.66

ongyang

-0.64

Ģ

-0.63

arms

-0.60

 pride

-0.60

HAEL

-0.59

 Kinnikuman

-0.59

ridges

-0.58

 cheeks

-0.57

orie

-0.57

POSITIVE LOGITS

ited

0.93

vironment

0.93

cend

0.91

thal

0.90

ction

0.89

swer

0.83

issance

0.83

ity

0.82

emies

0.82

cing

0.81

Activations Density 0.025%

proper nouns or names

mentions of specific individuals or names

No Comments

No Known Activations